Javascript must be enabled to continue!
A robust deformed convolutional neural network (CNN) for image denoising
View through CrossRef
Abstract
Due to strong learning ability, convolutional neural networks (CNNs) have been developed in image denoising. However, convolutional operations may change original distributions of noise in corrupted images, which may increase training difficulty in image denoising. Using relations of surrounding pixels can effectively resolve this problem. Inspired by that, we propose a robust deformed denoising CNN (RDDCNN) in this paper. The proposed RDDCNN contains three blocks: a deformable block (DB), an enhanced block (EB) and a residual block (RB). The DB can extract more representative noise features via a deformable learnable kernel and stacked convolutional architecture, according to relations of surrounding pixels. The EB can facilitate contextual interaction through a dilated convolution and a novel combination of convolutional layers, batch normalisation (BN) and ReLU, which can enhance the learning ability of the proposed RDDCNN. To address long‐term dependency problem, the RB is used to enhance the memory ability of shallow layer on deep layers and construct a clean image. Besides, we implement a blind denoising model. Experimental results demonstrate that our denoising model outperforms popular denoising methods in terms of qualitative and quantitative analysis. Codes can be obtained at
https://github.com/hellloxiaotian/RDDCNN
.
Institution of Engineering and Technology (IET)
Title: A robust deformed convolutional neural network (CNN) for image denoising
Description:
Abstract
Due to strong learning ability, convolutional neural networks (CNNs) have been developed in image denoising.
However, convolutional operations may change original distributions of noise in corrupted images, which may increase training difficulty in image denoising.
Using relations of surrounding pixels can effectively resolve this problem.
Inspired by that, we propose a robust deformed denoising CNN (RDDCNN) in this paper.
The proposed RDDCNN contains three blocks: a deformable block (DB), an enhanced block (EB) and a residual block (RB).
The DB can extract more representative noise features via a deformable learnable kernel and stacked convolutional architecture, according to relations of surrounding pixels.
The EB can facilitate contextual interaction through a dilated convolution and a novel combination of convolutional layers, batch normalisation (BN) and ReLU, which can enhance the learning ability of the proposed RDDCNN.
To address long‐term dependency problem, the RB is used to enhance the memory ability of shallow layer on deep layers and construct a clean image.
Besides, we implement a blind denoising model.
Experimental results demonstrate that our denoising model outperforms popular denoising methods in terms of qualitative and quantitative analysis.
Codes can be obtained at
https://github.
com/hellloxiaotian/RDDCNN
.
Related Results
Methods for image denoising using convolutional neural network: a review
Methods for image denoising using convolutional neural network: a review
AbstractImage denoising faces significant challenges, arising from the sources of noise. Specifically, Gaussian, impulse, salt, pepper, and speckle noise are complicated sources of...
Filtering Methods for Biomedical Image Denoising
Filtering Methods for Biomedical Image Denoising
In this paper, the filtering method of biomedical image denoising is described comprehensively. Firstly, it introduces the biomedical image denoising, describes the relationship be...
Analog Convolutional Operator Circuit for Low-Power Mixed-Signal CNN Processing Chip
Analog Convolutional Operator Circuit for Low-Power Mixed-Signal CNN Processing Chip
In this paper, we propose a compact and low-power mixed-signal approach to implementing convolutional operators that are often responsible for most of the chip area and power consu...
Analisis Pengaruh Diameter Kawat terhadap Distribusi Kapasitansi dari Wire Mesh Sensor Tomography menggunakan Convolutional Neural Network
Analisis Pengaruh Diameter Kawat terhadap Distribusi Kapasitansi dari Wire Mesh Sensor Tomography menggunakan Convolutional Neural Network
AbstrakWire Mesh Sensor (WMS) adalah sensor berbasis tomografi yang menghasilkan gambar distribusi aliran fluida. Citra distribusi merupakan pola distribusi kapasitansi yang diukur...
Penerapan Metode Convolutional Neural Network untuk Diagnosa Penyakit Alzheimer
Penerapan Metode Convolutional Neural Network untuk Diagnosa Penyakit Alzheimer
Abstract— Alzheimer's disease is a neurodegenerative disease that develops gradually, and is associated with cardiovascular and cerebrovascular problems. Alzheimer's is a serious d...
Improving Traffic Sign Recognition by Using Wavelet Convolutional Neural Network
Improving Traffic Sign Recognition by Using Wavelet Convolutional Neural Network
Traffic sign recognition (TSR) considered as a challenging subject in image processing for many years. Nowadays, after achievements in processing power of processors and easily acc...
Automated Image Denoising Model: Contribution Towards Optimized Internal and External Basis
Automated Image Denoising Model: Contribution Towards Optimized Internal and External Basis
For handling digital images for various applications, image denoising is considered as a fundamental pre-processing step. Diverse image denoising algorithms have been introduced in...
Implementasi Convolutional Neural Network dalam Mengenali Image Angka Tulisan Tangan
Implementasi Convolutional Neural Network dalam Mengenali Image Angka Tulisan Tangan
Abstract. Advances in information technology and artificial intelligence, particularly in the field of machine learning, have had a significant impact on various aspects of daily l...

